Hindawi

International Journal of Biomedical Imaging

Volume 2018, Article ID 5812872, 12 pages
https://doi.org/10.1155/2018/5812872

Research Article
An Automated Approach for Epilepsy Detection Based on
Tunable Q-Wavelet and Firefly Feature Selection Algorithm

Ahmed I. Sharaf ,1,2 Mohamed Abu El-Soud,1,3 and Ibrahim M. El-Henawy4

1
Department of Computer Science, Faculty of Computers and Information, El-Mansoura University, Egypt
2
Deanship of Scientific Research, Umm Al-Qura University, Mecca, Saudi Arabia
3
Department of Computer Science, University College of Umluj, Tabuk University, Saudi Arabia
4
Department of Computer Science, Faculty of Computers and Information, El-Zagazig University, Egypt

Correspondence should be addressed to Ahmed I. Sharaf; ahmed.sharaf.84@gmail.com

Received 20 April 2018; Revised 18 August 2018; Accepted 27 August 2018; Published 10 September 2018

Academic Editor: A. K. Louis

Copyright © 2018 Ahmed I. Sharaf et al. This is an open access article distributed under the Creative Commons Attribution License,
which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Detection of epileptic seizures using an electroencephalogram (EEG) signals is a challenging task that requires a high level of
skilled neurophysiologists. Therefore, computer-aided detection provides an asset to the neurophysiologist in interpreting the EEG.
This paper introduces a novel approach to recognize and classify the epileptic seizure and seizure-free EEG signals automatically
by an intelligent computer-aided method. Moreover, the prediction of the preictal phase of the epilepsy is proposed to assist the
neurophysiologist in the clinic. The proposed method presents two perspectives for the EEG signal processing to detect and classify
the seizures and seizure-free signals. The first perspectives consider the EEG signal as a nonlinear time series. A tunable Q-wavelet is
applied to decompose the signal into smaller segments called subbands. Then a chaotic, statistical, and power spectrum features sets
are extracted from each subband. The second perspectives process the EEG signal as an image; hence the gray-level co-occurrence
matrix is determined from the image to obtain the textures of contrast, correlation, energy, and homogeneity. Due to a large number
of features obtained, a feature selection algorithm based on firefly optimization was applied. The firefly optimization reduces the
original set of features and generates a reduced compact set. A random forest classifier is trained for the classification and prediction
of the seizures and seizure-free signals. Afterward, a dataset from the University of Bonn, Germany, is used for benchmarking
and evaluation. The proposed approach provided a significant result compared with other recent work regarding accuracy, recall,
specificity, F-measure, and Matthew’s correlation coefficient.

1. Introduction Epilepsy is usually characterized by two or more unpro-

Epilepsy is a chronic brain disease that affects people of all
ages. According to the World Health Organization (WHO),
approximately 65 million people suffer from this disorder [1],
the majority of whom reside in developing countries and can-
not obtain adequate medical treatment. Epilepsy doubles or
triples the probability of sudden death when compared with
that for healthy people [2]. Moreover, epileptic patients suffer
from social stigma and discrimination in their communities.
This stigma has a negative impact upon the quality of life
of patients and their families. Therefore, the investigation of
epilepsy detection techniques and antiepileptic drugs could
increase the probability of those coping with this disease to
live healthily without social stigmas.
voked seizures, which affect the ictal person at any time. An
elliptic seizure is defined as an excessive electrical discharge
in an arbitrary portion of the brain. This rapid discharge
causes a disturbance and abnormal behavior in the nervous
system. An adequate clinical tool used to recognize epileptic
seizures is the EEG signal analysis, as it measures the electro-
physiological signals of the brain in real time and measures
brain conditions efficiently [3]. However, EEG signal analysis
has some limitations in detecting elliptic seizures because of
epilepsy behavior such as the following:
(1) The occurrence of some seizures is not always because
of the epilepsy disorder, as approximately 10% of
healthy people may suffer from one seizure in their
2 International Journal of Biomedical Imaging
lifetime. These nonepileptic seizures are similar to
epileptic seizures, but they are not related to epilepsy
[2]. Hence, the classification of both epileptic and
nonepileptic seizures is further significant.
(2) Although qualified professional neurologists can
visually detect epileptic seizures from an EEG data
sheet, it is still considered a time-consuming process.
The diagnostics of epilepsy are usually performed by manual
inspections of the EEG signals which not an easy task and
requires a highly skilled neurophysiologist. Also, the manual
inspection of a long interval recording is a tedious and
time-consuming process. Therefore, an intelligent clinical
computer-aided design (CAD) tool that analyzes the EEG
signal and detects the epileptic seizure is required.
Various case studies have reported the advantages of
using automated methods to recognize epileptic seizures
from EEG signals. Many techniques are commonly employed
for automated EEG analysis and epilepsy detection. Most
of these techniques consist of two stages: the first is con-
cerned with feature extraction from the raw EEG signal;
the other is dedicated to classifying the features [2]. The
feature extraction process is concerned with obtaining sig-
nificant information from the raw EEG data as well, as it
could be implemented in the time, frequency, and time-
frequency domains. The time domain and frequency domain
are used for signal processing when the EEG is assumed to
be a stationary signal. On the other hand, when the EEG
signal is considered nonstationary [4, 5], then the time-
frequency domain is employed. Case studies demonstrated
that the time-frequency domain is more suitable for EEG
signal analysis and could obtain significant results [2]. Many
algorithms have been proposed for elliptic seizure detection
within the time-frequency domain such as empirical mode
decomposition (EMD) [6, 7] and wavelet transformation [8–
10]. The EMD methods provided a leading trend to detect
elliptic seizures from the EEG signal. The EMD has been
combined with 2D and 3D phase space representation (PSR)
features to identify elliptic seizures. Then, a least-squares
support vector machine (LS-SVM) is used to perform the
classification process [11]. A combination of different intrinsic
mode functions (IMFs) is constructed as a set of features
to utilize the classification problem [12]. The EMD has also
been used to decompose an EEG signal into a collection of
symmetric and band-limited signals. Then, a second-order
difference plot (SODP) is applied to obtain an elliptical area.
The area under this shape with 95% confidence is used
as a selection measure fed to an artificial neural network
(ANN) to determine the seizures and seizure-free signals [6].
Although the EMD methods proved their effectiveness, these
methods suffer from the mode-mixing problem, which pro-
duces intermediate signals and noise. Local Binary Pattern
(LBP) based methods represents a different approach of the
epilepsy detection. The work presented by [13] suggested a
feature extraction based on one dimensional LBP to classify
the epileptic seizure, seizure-free, and the healthy classes
from the EEG signal. In [14], the researchers have imple-
mented a technique based on the combination of the LBP
and the Gabor filter of the EEG signals. Then, the k-nearest
neighbor classifier was used for the classification of epileptic
seizures and seizure-free signals. The wavelet transformation
is usually employed with nonlinear measures to recognize
seizures and seizure-free patients from raw EEG signals.
An automatic epilepsy detection approach proposed by [15]
used the discrete wavelet transformation (DWT) for signal
decomposition and generated a feature set using improved
correlation-based feature selection (ICFS). Then, the random
forest classifier is applied for classification. The DWT has
been used with many nonlinear features, and the effectiveness
of this approach has been proved [16–23]. Although wavelet
transformation is an effective method for EEG signal analysis,
this transformation has some limitations [24]. The selection
of an appropriate wavelet bias is vital in the time-frequency
signal analysis.
A flexible wavelet transformation proposed by [25],
namely, tunable Q-wavelet transformation (TQWT), controls
the transformation of a discrete time signal by an easily
tunable variable called the Q-factor. The TQWT solved the
primary limits of the wavelet filter banks by providing a tun-
able Q-factor that controls the number of the oscillations of
the wavelet transformation. Moreover, the TQWT decreased
the search space of filter banks by providing three variables
only for adjusting. Also, many researchers applied TQWT for
physiological signal analysis and proved its effectiveness [21,
22, 26, 27]. However, the after-mentioned methods provided
a static set of features (e.g., statistical, nonlinear, and spectral)
and did not discuss the adaptive behavior of these features as
a dynamical system.
In this paper, an intelligent computer-aided design (CAD)
tool that analyses the EEG signal and classifies the epileptic
seizure and the seizure-free signal from the input EEG. That
provides an asset to the neurophysiologist in interpreting the
EEG and reduces the diagnostics time. The proposed method
is based on data fusion of a single-channel EEG signal and an
image processing approach. In the single-channel EEG signal,
the EEG data are processed as a time-frequency time series.
The signal is divided into smaller segments of data using
tunable Q-wavelet. Some statistical features are extracted
from this time series in the time domain and frequency
domain. On the other hand, an image processing technique
extracts the significant texture from the medical image. Thus,
the gray-level co-occurrence matrix is applied to the image,
and the contrast, correlation, energy, and homogeneity are
extracted. The data fusion approach is used to combine these
features of the input EEG signal and construct a large dataset
for each patient. Because of a large number of the extracted
features, a feature reduction algorithm is needed to reduce
the processing time by obtaining a compact subset of features
instead of the original one. Moreover, the feature reduction
algorithm selects the relevant features, removes redundant
features, and discovers the dependency among these features.
Therefore, the firefly algorithm is used to find the optimal
subset of features. Consequently, bootstraps are obtained by
resampling the compact subset to train the random forest
classifier. The final decision is obtained by performing a vote
for each decision tree of the forest. Hence, the classification
of seizure and seizure-free is obtained. A real-world dataset
from the University of Bonn is used for benchmarking and
International Journal of Biomedical Imaging 3

validation of the proposed method. A numerical experiment calculated from the time domain of the input signal. This
has been implemented, and a comparative study presented feature set contains mean (𝜇), standard deviation (𝑆𝑇𝐷), vari-
a promising efficiency of the proposed system regarding the ance (var), Shannon entropy (𝐻), and approximate entropy
overall accuracy, sensitivity, and specificity. (ApEn). The mathematical formulation of each feature is
The remainder of this manuscript is organized as follows: shown as follows [28–31]:
the preliminaries concepts were introduced in Section 2.
Section 3 introduced the combinational hybrid system of 1 𝑁
𝜇 (𝑥) = ∑𝑥 (5)
the epilepsy detection. The experiment and discussion were 𝑁 𝑖=1 𝑖
presented in Section 4. Lastly, the paper was concluded in
Section 5. 1 𝑁 2
𝑆𝑇𝐷 (𝑥) = √ ∑ (𝑥𝑖 − 𝜇𝑥 ) (6)
𝑁 − 1 𝑖=1
2. Preliminary Knowledge
1 𝑁 󵄨󵄨 󵄨2
2.1. Tunable Q-Wavelet Transformation (TQWT). The tun- var (𝑥) = ∑ 󵄨𝑥 − 𝜇󵄨󵄨󵄨 (7)
ability of the Q-factor provided a proficient method to adopt 𝑁 − 1 𝑖=1 󵄨 𝑖
the wavelet transformation [25]. The TQWT have three
𝑁
inputs: Q-factor denoted by 𝑄, which determines the number
𝐻 (𝑋) = ∑𝑃 (𝑥𝑖 ) log (𝑃 (𝑥𝑖 )) (8)
of oscillations of the wavelet; the number of the oversampling 𝑖=1
rate, which is denoted by 𝑟 and which determines the number
of the overlapping frequency responses; and the number of 𝐴𝑝𝐸𝑛 (x) = 𝜙𝑚 (𝑟) − 𝜙𝑚+1 (𝑟) . (9)
stages of decomposition, denoted by 𝐽. For each decomposi-
The second set of features calculates the power spectrum of
tion stage, the target signal 𝑠[𝑛] with a sample rate of 𝑓𝑠 could
the input signal based on the frequency domain analysis.
be represented by low-pass and high-pass subbands with
This feature set contains spectral centroid (𝑆𝐶), spectral speed
sampling frequencies of 𝛼𝑓𝑠 and 𝛽𝑓𝑠 , respectively, where 𝛼 and
(𝑆𝑆), spectral flatness (𝑆𝐹), spectral slope (𝑆𝑆𝐼), and spectral
𝛽 are the parameters of signal scaling. The low-pass subband
entropy (𝑃𝑆𝐸), where 𝑌(𝑞) denotes the for the discrete
is presented by low-pass filter 𝐻0 (𝜔) and low-pass scaling
Fourier transformation of the input signal 𝑓(𝑛). The math-
𝐿𝑃𝑆(𝛼). Similarly, the high-pass subband 𝜔1 is produced by
ematical formulation of each feature is shown as follows [32]:
𝐻1 (𝜔) and 𝐻𝑃𝑆(𝛽). The low-pass and high-pass subband
󵄨󵄨 󵄨󵄨
signals are formulated as follows: ∑𝑀−1
𝑞=0 𝑞 󵄨󵄨𝑌 (𝑞)󵄨󵄨
𝑆𝐶 = 𝑀−1 󵄨 󵄨 (10)
H𝑐0 (𝜔) ∑𝑞=0 󵄨󵄨󵄨𝑌 (𝑞)󵄨󵄨󵄨
2 󵄨󵄨 󵄨󵄨
{ 0, 𝛼𝜋 ≤ |𝜔| ≤ 𝜋 } ∑𝑀−1
𝑞=0 (𝑞 − 𝑆𝐶) 󵄨󵄨𝑌 (𝑞)󵄨󵄨
{
{ }
} 𝑆𝑆 = (11)
{ 𝜔 + (𝛽 − 1) 𝜋 } (1)
󵄨󵄨 󵄨󵄨
= {𝜃 ( ) , (1 − 𝛽) 𝜋 ≤ |𝜔| < 𝛼𝜋 ∑𝑀−1
𝑞=0 󵄨󵄨𝑌 (𝑞)󵄨󵄨
{ }
}
{
{ 𝛼+𝛽−1 }
} 󵄨󵄨 󵄨󵄨1/𝑀
{ 1, |𝜔| < (1 − 𝛽) 𝜋 } ∏𝑀−1
𝑞=0 󵄨󵄨𝑌 (𝑞)󵄨󵄨
𝑆𝐹 = 𝑀−1 󵄨 󵄨 (12)
{ 0, |𝜔| < (1 − 𝛽) 𝜋 } (1/𝑀) ∑𝑞=0 󵄨󵄨󵄨𝑌 (𝑞)󵄨󵄨󵄨
{
{ }
}
{ 𝛼𝜋 − 𝜔 }
H1 (𝜔) = {𝜃 ( , 𝑀 ∑𝑀−1 󵄨󵄨 󵄨󵄨 𝑀−1 𝑀−1 󵄨󵄨 󵄨󵄨
) , (1 − 𝛽) 𝜋 ≤ < 𝛼𝜋 𝑞=0 𝑓𝑚 󵄨󵄨𝑌 (𝑞)󵄨󵄨 − ∑𝑞=0 𝑓𝑚 ⋅ ∑𝑞=0 󵄨󵄨𝑌 (𝑞)󵄨󵄨
|𝜔| } (2)
{ }
{ 𝛼+𝛽−1
{ }
} SSI = (13)
2 − (∑𝑀−1 󵄨󵄨𝑌 (𝑞)󵄨󵄨)
2
{ 1, 𝛼𝜋 ≤ |𝜔| ≤ 𝜋 } 𝑀∑𝑀−1 𝑞=0 𝑓𝑚 󵄨
𝑞=0 󵄨 󵄨
󵄨
where 𝜃(𝜔) could be defined as follows: 𝑛
𝑌 (𝑞) 𝑌 (𝑞)
𝑃𝑆𝐸 = −∑ 𝑛 ln ( 𝑛 ) (14)
𝜃 (𝜔) = 0.5 (1 + cos (𝜔)) (2 − cos (𝜔))0.5 , |𝜔| ≤ 𝜋 (3) 𝑖=1 ∑𝑖=1 𝑌 (𝑞) ∑𝑖=1 𝑌 (𝑞)
The third set of features contains chaotic measures to obtain
Both of 𝑟 and 𝑄 could be represented as filter-bank variables the dynamic behavior of the EEG signal. This set includes
𝛼 and 𝛽 as follows: Higuchi’s fractal dimension (𝐻𝐹𝐷), Hurst exponent (𝐻𝑟 ),
𝛽 and Katz fractal exponent (𝐾𝐴𝑇𝑍). These features are
𝑟= , formulated as follows [33–36]:
1−𝛼
(4) 𝑘
2−𝛽 𝐻𝐹𝐷 = ln ( ) (15)
𝑄= . 𝐿 (𝑘)
𝛽
𝑅 (𝑛)
𝐸[ ] = 𝑐𝑛𝐻𝑟 (16)
2.2. Feature Sets. The feature sets used in this research are 𝑆 (𝑛)
grouped into four main groups which are statistical, power
log (𝑛)
spectrum, chaotic features, and gray-level co-occurrence 𝐾𝐴𝑇𝑍 = (17)
matrix (GLCM). The first group contains a set of five features log (𝑛) + log (𝑑/𝐿)
4 International Journal of Biomedical Imaging

The final set of features consists of statistical measures 3. The Combinational Hybrid System of
of an image represented as matrices called gray-level co- Epilepsy Detection from EEG Signal
occurrence matrix (GLCM) where 𝐶(𝑖, 𝑗) represents an entry
in co-occurrence matrix and 𝑖, 𝑗 = 0, 1, 2, . . . 𝐿 − 1, where In this research, a hybrid system was proposed to detect
𝐿 is the number of gray levels in the image. Those matrices both seizures and seizure-free conditions from a raw EEG
represent the spatial dependencies between the gray levels of signal. Although some investigations focused on the feature
image reflecting the structure of the underlying texture. After extraction level, the proposed system was established based
the normalization of these matrices, the contrast, correlation, on four main levels. This system combined the data fusion
energy, and homogeneity are computed as follows: approach with firefly optimization and random forest. The
𝑇𝑄𝑊𝑇 was applied for EEG signal decomposition; then the
𝐿−1 𝐿−1 features were constructed using a data fusion technique. Due
2
𝐸𝑛𝑒𝑟𝑔𝑦 = ∑ ∑ 𝐶 (𝑖, 𝑗) (18) to the large number of features obtained for each subband
𝑖=0 𝑗=0 (𝑓𝑒𝑎𝑡𝑢𝑟𝑒𝑠𝐶𝑜𝑢𝑛𝑡 × 𝐽 × 𝑄), a feature reduction was applied to
𝐿−1 𝐿−1
reduce the features and to obtain a compact set of features
2 instead of the original one. The obtained compact set of
𝐶𝑜𝑛𝑡𝑟𝑎𝑠𝑡 = ∑ ∑ (𝑖 − 𝑗) 𝐶 (𝑖, 𝑗) (19)
𝑖=0 𝑗=0
features was fed to a random forest algorithm to obtain
the classification rules and hence used for training. After
𝐿−1 𝐿−1 (𝑖 − 𝜇𝑖 ) (𝑗 − 𝜇𝑗 ) 𝐶 (𝑖, 𝑗) training, the classifier should be able to classify and estimate
𝐶𝑜𝑟𝑟𝑒𝑙𝑎𝑡𝑖𝑜𝑛 = ∑ ∑ (20) the preictal phase. The proposed system was divided into
𝑖=0 𝑗=0 𝜎𝑖 𝜎𝑗 the following four levels of processing and then described in
𝐿−1 𝐿−1
detail as shown in Figure 1.
1
𝐿𝑜𝑐𝑎𝑙 ℎ𝑜𝑚𝑜𝑔𝑒𝑛𝑒𝑖𝑡𝑦 = ∑ ∑ 2
𝐶 (𝑖, 𝑗) (21) (i) EEG decomposition using TQWT
𝑖=0 𝑗=0 1 + (𝑖 − 𝑗)
(ii) Feature extraction using data fusion based on single-
channel EEG signal and co-occurrence matrix
2.3. Firefly Optimization Algorithm. The firefly algorithm is
a swarm based stochastic search technique [37]. The firefly (iii) Feature reduction using firefly optimization algo-
optimization algorithm consists of a set of members called rithm
fireflies; each firefly represents a candidate solution. The (iv) Training of random forest classifier to detect the
most attractive firefly is considered to be the leader firefly seizures and seizure-free EEGs
that leads the other candidates to the best region. The
attractiveness is calculated based on the light intensity which 3.1. EEG Decomposition Using TQWT. The preprocessing
is usually determined by the objective fitness function. The level applies the 𝑇𝑄𝑊𝑇 decomposition to the input EEG
attractiveness between two fireflies 𝑋𝑖 and 𝑋𝑗 is determined signal. The 𝑇𝑄𝑊𝑇 converted the continuous EEG signal
as follows: to discrete potions of data that could be handled more
2 effectively. This wavelet transformation is used because of its
𝛽 (𝑟𝑖𝑗 ) = 𝛽0 𝑒−𝛾𝑟𝑖𝑗 (22) effectiveness in signal decomposition and its tunability. The
obtained subbands using the 𝑇𝑄𝑊𝑇 provided a significant
𝐷
2
difference between the seizure-free and the epileptic seizure
𝑟𝑖𝑗 = √ ∑ (𝑥𝑖𝑑 − 𝑥𝑗𝑑 ) (23) of the EEG signals as shown in Figure 2. The subfigures
𝑑=1 denoted by (a), (b), (c), and (d) visualize the histogram of the
first, second, third, and fourth subbands of the seizure-free
where 𝐷 denotes the problem dimension such that 𝐷 = class. The remaining subfigures denoted by (e), (f), (g), and
{1, 2, . . . , 𝑑}, 𝑟𝑖𝑗 denotes the distance between 𝑋𝑖 and 𝑋𝑗 . (h) represent the histogram of the epileptic seizure class for
Parameter 𝛽0 denotes the initial attractiveness at 𝑟 = 0 and the same subbands. The values of the extracted subbands of
𝛾 denotes the light absorption factor such that 𝛾 ∈ [0, 1]. the second class are about ten times stronger than the first
Each firefly 𝑋𝑖 is compared with the other fireflies 𝑋𝑗 where class that prove the efficiency of this decomposition.
𝑗 ∈ {1, 2, . . . 𝑁} such that 𝑖 ≠ 𝑗 and 𝑁 denotes the count of the
fireflies. If firefly 𝑋𝑖 is better (brighter) than 𝑋𝑗 , then firefly 3.2. Feature Extraction Using Data Fusion Based on a Single-
𝑋𝑗 moves towards 𝑋𝑖 with a step movement formulated as Channel EEG and a Co-Occurrence Matrix. In the first
follows: perspective, the EEG signal was described as a nonstationary
−𝛾𝑟𝑖𝑗2
time series. After the decomposition of the EEG signal using
𝑋𝑖𝑑 (𝑡 + 1) = 𝑋𝑖𝑑 (𝑡) + 𝛽0 𝑒𝑖𝑗 (𝑋𝑗𝑑 (𝑡) − 𝑋𝑖𝑑 (𝑡)) the TQWT, a feature extraction process was performed to
(24) obtain significant characteristics from each TQWT subbands.
+ 𝛼𝜖𝑖 The extracted features were categorized into three main
groups. The first group determines the statistical character-
where 𝜖𝑖 represents uniform a randomly distributed variable istics in the time domain. The mean, standard deviation,
such that 𝜖𝑖 ∈ [−0.5, 0.5] and 𝛼 denotes the movement step variance, Shannon entropy, and approximate entropy were
such that 𝛼 ∈ [0, 1]. calculated in the first group as formulated from (5) to (9).
International Journal of Biomedical Imaging 5

Extract
Image Apply TQWT for the chaotic features
signal decomposition Train the random forest
classifier
Extract Constrcut feature
statistical features Feature reduction using
space using data firefly algorithm End
EEG Signal fusion
Extract Classifiy and estimate
power spectrum seizures using the trained
features model

Extract
Single EEG Channel Co-occurrence
matrix
Input Level 1 Level 2 Level 3 Level 4

Figure 1: Block diagram of the combinational hybrid system of epilepsy detection from EEG signal with 4 levels of processing.

2500 3000 1400 1200

2500 1200
2000 1000
1000
2000 800
1500
occurance
occurance

occurance

occurance
800
1500 600
1000 600
1000 400
400
500 500 200 200

0 0 0 0
−20 0 20 −40 −20 0 20 40 −50 0 50 100 −200 0 200 400
V V V V

(a) (b) (c) (d)

2500 2500 1200 1200

2000 2000 1000 1000

800 800
1500 1500
occurance

occurance

occurance

600 occurance 600

1000 1000
400 400
500 500
200 200

0 0 0 0
−200 0 200 −400 −200 0 200 400 −500 0 500 −1000 −500 0 500 1000
V V V V

(e) (f) (g) (h)

Figure 2: Illustration of seizure-free and epileptic seizures of subbands obtained from TQWT with Q = 1, r = 3, J = 3. Figures (a), (b), (c),
and (d) represent the first, second, third, and fourth subbands obtained from seizure-free signals. Figures (e), (f), (g), and (h) represent the
first, second, third, and fourth subbands obtained from the epileptic seizures.

This group indicates some statistical information obtained exponent, and Katz fractal exponent were computed for each
from the time domain of TQWT subband. The second subband as formulated from (15) to (18).
group of features determines a power spectrum analysis In the second perspective, the input EEG signal was
of obtained subbands. The discrete Fourier transformations converted to a gray image. Then a co-occurrence matrix was
(DFT) were applied to convert these subbands into a fre- computed to obtain the gray levels of the image. Then the
quency domain. Then the power spectrum features were textures of contrast, correlation, energy, and homogeneity
extracted. The second group consists of the spectral centroid, were calculated from this matrix to represent the statistical
spectral speed, spectral flatness, spectral slope, and spectral measures of the image as formulated from (19) to (21). Finally,
entropy as formulated from (10) to (14). The power spectrum after computing the feature space, a data fusion was applied
analysis represents an effective method to study the frequency to merge all of these features and create a single dataset.
behavior of the signal. The last group of features performs a
chaotic analysis of each subband. Because of the nonlinearity 3.3. Feature Reduction Using Firefly Optimization Algorithm.
of the EEG signals, a nonlinear analysis is required. One of In this section, a feature reduction algorithm based on
the best analyses used for this issue is the chaotic analysis. the firefly algorithm is proposed [37, 38]. This algorithm
In this analysis, the Higuchi fractal dimension (HFD), Hurst implements a chaotic movement, simulated annealing (SA)
6 International Journal of Biomedical Imaging

(1) Input: The features matrix 𝐹𝑚

(2) Output: The optimal solution 𝑔𝑏𝑒𝑠𝑡
(3) Initialize the firefly swam using a logistic chaotic map.
(4) Evaluate each firefly 𝑔𝑖 using the fitness function f (x)
(5) Select the best firefly 𝑔𝑏𝑒𝑠𝑡 and the worst one 𝑔𝑤𝑜𝑟𝑠𝑡
(6) while termination condition are not reached do
(7) Declare an alternative leader firefly as 𝑆𝑏𝑒𝑠𝑡 , with a competitive fitness and located in different region.
(8) Obtain an offspring solution 𝑔𝑏𝑒𝑠𝑡 using 𝑆𝐴.
(9) for all (firefly 𝑖 and 𝑓𝑖 ≠ 𝑔𝑤𝑜𝑠𝑟𝑡 ) do
(10) for all (firefly 𝑗 and 𝑓𝑗 ≠ 𝑔𝑤𝑜𝑠𝑟𝑡 ) do
(11) if (𝐼𝑗 > 𝐼𝑖 ) then
(12) Enhance firefly 𝑗 using Equation (25) to obtain better offspring candidate firefly denoted 𝑥𝑗󸀠
(13) Replace firefly 𝑗 with the offspring 𝑥𝑗󸀠
(14) Move the firefly 𝑗 towards the neighboring and global optimal solutions using Equation (26)
(15) end if
(16) end for
(17) end for
(18) Update the worst solution 𝑔𝑤𝑜𝑟𝑠𝑡
󸀠
(19) if 𝑓(𝑔𝑏𝑒𝑠𝑡 ) > 𝑓(𝑔𝑏𝑒𝑠𝑡 ) then
󸀠
(20) 𝑔𝑏𝑒𝑠𝑡 ←󳨀 𝑔𝑏𝑒𝑠𝑡
(21) end if
(22) Rank all fireflies and update the best 𝑔𝑏𝑒𝑠𝑡 and worst 𝑔𝑤𝑜𝑟𝑠𝑡 solutions.
(23) end while
(24) return 𝑔𝑏𝑒𝑠𝑡

Algorithm 1: The pseudocode of the proposed feature reduction algorithm based on firefly optimization and SA.

to produce efficient offspring candidates, and memory aware-
ness of the best and worst solutions to improve the search
diversity and prevent local optima. The firefly population is
randomly initialized using a chaotic logistic map to ensure
the diversely of the candidates and the randomness of each
firefly. Afterwards, the fitness function is computed for each
candidate and identifies both the best and worst solutions as
𝑔𝑏𝑒𝑠𝑡 and 𝑔𝑤𝑜𝑠𝑟𝑡 , respectively. For each iteration, an alternative
candidate is declared as 𝑆𝑏𝑒𝑠𝑡 with a competitive fitness
and located in a different region. Both of the best and the
alternative candidate sets are used to lead weak solutions to
reach the optimal region and prevent local optima problem.
The mean of the leader firefly and the alternative one is
enhanced using SA algorithm to obtain a better solution
󸀠
𝑔𝑏𝑒𝑠𝑡 . The improved local and global solutions are used to
guide the low lightness fireflies to move towards that stronger
lightness. The algorithm is repeated until the maximum
number of iterations is reached, or a termination criterion is
achieved. The behavior of the proposed algorithm is deter-
mined by some properties, namely, the objective function, the
attractiveness movement step, and population diversity. The
proposed algorithm is demonstrated in Algorithm 1.
The Objective Function. This function is used to evaluate each
candidate in the algorithm and defined as follows:
𝑤2
𝑓 (𝑥) = 𝑤1 × 𝑎𝑐𝑐𝑢𝑟𝑎𝑐𝑦 (𝑥) +
number of features
where 𝑤1 and 𝑤2 represent the weights of the classifi-
cation accuracy and the number of the selected features,
respectively. The values of 𝑤1 and 𝑤2 are set to 0.9 and 0.1,
respectively, as a recommended by [38].
The Attractiveness Movement Step. The proposed algorithm
used a chaotic logistic map to initialize the firefly population
and hence increases the diversity and avoid local optima.
After obtaining the global best solution 𝑔𝑏𝑒𝑠𝑡 , an alternative
leader firefly 𝑆𝑏𝑒𝑠𝑡 is declared with a competitive fitness but
located in a different region. Since both leaders are more
likely to discover distinctive search regions, this strategy
reduces the probability of being trapped in the local optima.
In addition, the optimal offspring of the mean positions of the
two leaders and the neighboring brighter candidates are used
to lead the search process and guide the solutions with lower
light intensity to move towards the optimal region.
𝑥𝑖 = 𝑥𝑖 + 𝛽0 𝐶𝑘 (𝑥𝑗󸀠 − 𝑥𝑖 ) + 𝐶𝑘 𝜀 (𝑔𝑏𝑒𝑠𝑡
󸀠
− 𝑥𝑖 ) + 𝛼󸀠
(26)
× sign [𝑟𝑎𝑛𝑑 − 0.5]
𝑥𝑗󸀠 = 𝑥𝑗 + 𝜎1 (27)
󸀠
𝑔𝑏𝑒𝑠𝑡 = 𝑚𝑒𝑎𝑛 (𝑔𝑏𝑒𝑠𝑡 + 𝑆𝑏𝑒𝑠𝑡 ) + 𝜎2 (28)
where 𝑥𝑗󸀠 denotes the offspring candidate with a brighter
neighboring solution, 𝑥𝑗 is defined by the SA as shown in (26),
󸀠
and 𝑔𝑏𝑒𝑠𝑡 represents the fitter offspring solutions of the mean
(25)
of the leader firefly and the alternative one as formulated in
(27). It worth mentioning that the values of 𝜎1 and 𝜎2 are
two random variables set using the Gaussian distribution.
The movement step of the firefly is determined as shown in
International Journal of Biomedical Imaging 7

(1) Input: 𝑖𝑡𝑒𝑟𝑎𝑡𝑖𝑜𝑛𝑠𝑚𝑎𝑥 , 𝑔𝑚𝑒𝑎𝑛 , 𝑇𝑚𝑎𝑥

(2) Output: The optimal offspring 𝑆𝑏𝑒𝑠𝑡
(3) 𝑆𝑐 = 𝐶𝑟𝑒𝑎𝑡𝑒𝐼𝑛𝑖𝑡𝑆𝑜𝑢𝑙𝑡𝑖𝑜𝑛𝑠(𝑔𝑚𝑒𝑎𝑛 )
(4) 𝑆𝑏𝑒𝑠𝑡 = 𝑆𝑐
(5) while (𝑖 ≤ 𝑖𝑡𝑒𝑟𝑎𝑡𝑖𝑜𝑛𝑠 𝑚𝑎𝑥) do
(6) 𝑆𝑖 = 𝐶𝑟𝑒𝑎𝑡𝑒𝑁𝑒𝑖𝑔ℎ𝑏𝑜𝑟𝑆𝑜𝑙𝑢𝑡𝑖𝑜𝑛(𝑆𝑐 )
(7) 𝑇𝑐 = 𝐶𝑎𝑙𝑐𝑢𝑙𝑎𝑡𝑒𝑇𝑒𝑚𝑝𝑒𝑟𝑎𝑡𝑢𝑟𝑒(𝑖, 𝑇𝑚𝑎𝑥 )
(8) if (𝑐𝑜𝑠𝑡(𝑆𝑖 ) ≤ 𝑐𝑜𝑠𝑡(𝑆𝑐 )) then
(9) 𝑆𝑐 = 𝑆𝑖
(10) if (𝑐𝑜𝑠𝑡(𝑆𝑖 ) ≤ 𝑐𝑜𝑠𝑡(𝑆𝑏𝑒𝑠𝑡 )) then
(11) 𝑆𝑏𝑒𝑠𝑡 = 𝑆𝑖
(12) end if
(13) else if (exp((𝑐𝑜𝑠𝑡(𝑆𝑏𝑒𝑠𝑡 ) − 𝑐𝑜𝑠𝑡(𝑆𝑖 ))/𝑇𝑐 ) ≥ 𝜎) then
(14) 𝑆𝑐 = 𝑆𝑖
(15) end if
(16) 𝑖 = 𝑖 + 1
(17) end while
(18) return 𝑆𝑏𝑒𝑠𝑡

Algorithm 2: The pseudocode of the generation of offspring solutions using SA.

(28), where 𝐶𝐾 represents the chaotic map variable in the
movement step and 𝜀 denotes the randomized vector defined
in the traditional firefly algorithm. Parameter 𝛼󸀠 denotes an
adaptive step initialized to 0.5 to control the diversity of the
search process.
Offspring Generation Using SA. The proposed algorithm used
SA for generating better candidates to enhance the search
process as much as possible as shown in Algorithm 2. The
SA accepts both of the best solution 𝑔𝑏𝑒𝑠𝑡 and the alternative
solution 𝑆𝑏𝑒𝑠𝑡 as main inputs, then the traditional SA is
applied. The better solution generated is accepted by default
according to the SA heuristics. On the other hand, the
weaker solution should be accepted with specific probability
as shown in (29), where Δ𝑓 denotes the difference of the
fitness (energy) between to candidates and 𝑇𝑐 denotes the
current temperature. A simple linear cooling mechanism is
used to control the value of the temperature.
Δ𝑓
𝑝𝑥𝑗 = exp ( ) (29)
𝑇𝑐
Population Diversity. In each iteration, the worst solution is
detected after the ranking process as shown in Algorithm 1.
The remaining solutions are guided by the average position
obtained from (30) where 𝜎 denotes a random value obtained
by Gaussian map.
𝑔𝑏𝑒𝑠𝑡 + 𝑆𝑏𝑒𝑠𝑡 𝑔 + 𝑆𝑏𝑒𝑠𝑡
𝑥𝑗𝑤𝑜𝑟𝑠𝑡 = + 𝜎 (𝑥𝑗𝑤𝑜𝑟𝑠𝑡 𝑏𝑒𝑠𝑡 ) (30)
2 2
3.4. Classification and Learning. The random forest (RF) is
a successful ensemble approach used in supervised machine
learning to solve classification or regression problems [39].
It consists of a collection of decision trees that could act
as a single classifier with multiple classification methods
or a method that has several variables. Several subsets of
the training data are supplied to each tree to achieve the
most stable tree classification that results in a generalized
experience of the classifier. The original dataset is divided
into two parts. The first part is used to train each tree by
bootstrapping technique. The other part is used to evaluate
the accuracy of the classification. Each tree is allowed to reach
the maximum depth without tree pruning to obtain a high
variance classifier. The splitting process remains until only
one instance of a single class is dropped from any leaf node
or a predefined termination condition is achieved. When
the forest is established, the number of subsets remained as
a constant. The obtained route of traversal from the root
node to the leaf node is applied to the new instances or
the unlabeled instance for classification. The final decision
for classifying a new instance is provided by determining
each class that has the most votes from every decision tree.
The random forest performs slightly better when compared
with other classifiers such as discriminant analysis, SVM, and
artificial neural network (ANN) [15, 39].
3.5. Performance Evaluation. Various performance formulas
were used to evaluate the effectiveness of a classifier. The sen-
sitivity (SEN) or recall, specificity (SPEC), accuracy (ACC),
F-measure, Matthew’s correlation coefficient (MCC), and
receiver operating characteristics (ROC) are used to evaluate
the efficiency of the random forest classifier [40–42]. These
parameters are defined as follows:
𝑇𝑃
𝑆𝐸𝑁 = × 100 (31)
𝑇𝑃 + 𝐹𝑁
𝑇𝑁
𝑆𝑃𝐸𝐶 = × 100 (32)
𝑇𝑁 + 𝐹𝑃
𝑇𝑃 + 𝑇𝑁
𝐴𝐶𝐶 = × 100 (33)
𝑇𝑃 + 𝑇𝑁 + 𝐹𝑃 + 𝐹𝑁
2𝑇𝑃
𝐹 − 𝑚𝑒𝑎𝑠𝑢𝑟𝑒 = × 100 (34)
2𝑇𝑃 + 𝐹𝑃 + 𝐹𝑁
8 International Journal of Biomedical Imaging
𝑀𝐶𝐶
(𝑇𝑃 × 𝑇𝑁) − (𝐹𝑃 × 𝐹𝑁)
= (35)
√(𝑇𝑃 + 𝐹𝑁) (𝑇𝑃 + 𝐹𝑃) (𝑇𝑁 + 𝐹𝑁) (𝑇𝑁 + 𝐹𝑃)
× 100
𝑇𝑃 and 𝑇𝑁 represent the total number of an epileptic seizure
and seizure-free signals classified correctly, respectively. Sim-
ilarly, 𝐹𝑃 and 𝐹𝑁 represent the total number of epileptic
seizures and seizure-free signals classified incorrectly, respec-
tively. Cross-validation has also been used to ensure the
classifier reliability and effectiveness. The original dataset is
split into 𝑘 folds (subsets) for both training and testing. In
this strategy, 𝑘 − 1 folds were selected randomly to train the
classifier, and the remaining folds are used to testing. The
overall performance is calculated as the average of each fold.
In this work, the experiment is repeated 10 times with tenfold
cross-validation.
4. Results and Discussion
The benchmark dataset used in this investigation was
acquired by the University of Bonn [28]. The dataset contains
three different categories, i.e., preictal, healthy, and ictal
recorded using a single channel for a 23.6 s duration. Both
normal and preictal conditions were collected from 200 case
studies and 100 for the ictal state. The normal condition is
acquired from five healthy volunteers using the international
10–20 system standard with each volunteer in a relaxed-
awake state with eyes open and closed (100 cases per each set)
[28]. The ictal data were collected from five patients during
their epileptic seizures. The preictal represents the EEG data
collected from the same five patients with no seizures. It is
worth mentioning that all EEG signals were acquired using a
128 channel amplifier with sampling rate equal 173.61 Hz [28].
Finally, a bandpass filter with 0.5340 Hz ∼12 dB/octave was
applied as a filter.
The proposed approach for automatic detection of epilep-
tic seizures and seizure-free patients was implemented using
MATLAB software. A TQWT comparison between the
seizure-free and the epileptic seizures patients are shown in
Figure 3 with 𝑄 = 1, 𝑟 = 3, and 𝐽 = 3. It can be observed
that both of the amplitudes and the frequency of the epileptic
seizure are much higher than the healthy one. Moreover, the
oscillatory behavior of the epileptic patient is higher than the
healthy one. The value of the parameter 𝑟 is set to three, to
prevent any excessive ringing of the wavelet as suggested by
[22]. MATLAB for the TQWT toolbox is available for public
access at http://eeweb.poly.edu/iselesni/TQWT/.
After the construction of the dataset, the feature reduc-
tion was applied using the firefly algorithm to remove the
redundant and irrelevant features. The number of the data
segments was determined by the parameters 𝑄, 𝑟, and 𝐽. By
tuning these parameters, the number of the data segments
was varied, and thus the training process was adopted. The
trial and error approach was used to set the value of these
parameters. The experiment was implemented on various
values of J to obtain the best level of decomposition. The
performance measures were calculated for each level of
decomposition. As shown in Figure 4, the best value of the
variable 𝐽 was from two to three. Moreover, the best value of
the parameter 𝑄 was found to be one as shown in Figure 5. All
the variables remained constant while changing the Q-factor
to obtain the best value.
Then, the firefly algorithm with a population size of 20
fireflies, mutation probability of 0.01, and light absorption
equal to 0.1 was applied to reduce the feature set. The result of
the compact set of features is obtained after 100 iterations and
shown in Figure 6 are the number of features obtained by the
firefly algorithm and their corresponding accuracy, precision,
specificity, and the recall. In the last step, the feature set is
fed to a random forest classifier to obtain the seizure-free and
seizure conditions. The random forest classifier obtained 98%
accuracy, 97% precision, 97% specificity, 98% recall, 98% F-
measure, and 95% MCC at the third level of decomposition,
and the Q-factor equals 1.
The firefly algorithm reduced the search space into three
features. These features could replace the original dataset
which minimizes the processing time. The compact set of
feature contains the 𝑆𝑇𝐷, 𝐴𝑝𝐸𝑛, and the 𝐾𝐴𝑇𝑍; the classi-
fication rules are based on these features. The classification
rules obtained by the proposed system are shown in Figure 7,
where the decision tree consists of 4 leaves and 7 nodes, and
the final decision represents the seizure-free and the epileptic
seizure denoted by 0,1, respectively.
A comparative study of the proposed hybrid epilepsy
detection approach and other existing classification systems
has been performed in terms of the total accuracy. A novel
method based on the EMDs was proposed to detect the
epileptic seizures of epilepsy. This method used the Hilbert
transformation of IMFs obtained by EMD process that
provided an analytic signal representation of IMFs [12]. The
classification rules obtained by this method achieved an
accuracy of 90%. The usage of frequency domain features
and Burg’s method obtained 93.11% accuracy with SVM
classifier [43]. Nonlinear features have been used with a
Gaussian mixture model classifier and achieved 95% accuracy
[44]. A decision tree classifier is used with energy, fractal
dimension, and sample entropy and provided 95.7% [45].
A combination of ApEn and the Hurst exponent has been
used to detect the diagnostics of epilepsy and produced 96.5%
accuracy with SVM classifier and ANN [46]. In [47], an
eigensystem based method was proposed cooperated with
Multiple Layer Perceptron to classify the epileptic seizures,
healthy, and the seizure-free. This approach provided an
average accuracy of 97.5%. The EMD methods for epilepsy
detection achieved 97.75% accuracy [6]. The Kraskov entropy
is also combined with the SVM classifier and provided 97.75%
[22]. An automated diagnostics system based on a set of
entropies and fuzzy Sugeno classifier (FSC) achieved accu-
racy up to 98% [19]. The work presented by [48] developed
a method for the epilepsy detection using the EMD. The
generated IMFs using the EMD were represented as a set of
amplitude and frequency modulated (AM–FM) signals. The
two bandwidths, namely, amplitude modulation bandwidth
and frequency modulation bandwidth, calculated from the
analytic IMFs, have been fed to LS-SVM for classifying
International Journal of Biomedical Imaging 9

SUBBAND

SUBBAND
1 1
2 2
3 3
4 4
0 500 1000 1500 2000 2500 3000 3500 4000 0 500 1000 1500 2000 2500 3000 3500 4000
TIME (SAMPLES) TIME (SAMPLES)
(a) EEG Sample for patient with seizure-free (b) EEG Sample for patient with seizures

Figure 3: TQWT decomposition of seizure-free and seizure EEG signals with 𝑄 = 1, 𝑟 = 3, 𝑗 = 3.

1.00 1
0.99
0.80 0.98
0.97
PERCENTAGE

PERCENTAGE
0.60 0.96
0.95
0.40 0.94
0.93
0.20 0.92
0.91
0.00 0.9
1 2 3 4 5 10 1 2 3 4 5
LEVELS OF DECMPOSISTION (J) NUMBER OF FEATURES

ACC SPEC ACC SPEC

Precision Recall Precision Recall
Figure 4: Performance measures of the proposed approach with Figure 6: Performance measures of the original and compact
varied levels of decomposition. features set.

1 STD
0.98
0.96
0.94 <= 28.73 > 28.73
PERCENTAGE

0.92
0.9 0 ApEn
0.88
0.86 <= 0.16 > 0.16
0.84
0.82
0.8 Katz 1
1 2 3 5 7 9 10
Q
<= 1.46 > 1.46

ACC SPEC
Precision 0 1
Recall

Figure 5: Performance measures of the proposed approach with Figure 7: The classification rules obtained from the proposed
varied levels of decomposition. system to classify the seizure-free (0) and the epileptic seizure (1)
signals.

seizure and nonseizure EEG signals. This method achieved

98.18% average accuracy. The LBP-based methods have been
combined with Gabor filter for texture extraction from the
EEG signal. A k-nearest neighbor classifier was applied and
obtained an accuracy of 98.3% [14]. The proposed method
confirmed its superiority in the total accuracy compared to
the other systems. The results, which prove the superiority of
the proposed method compared to the other existed systems,
is demonstrated in Figure 8.
Once the system detects the preictal phase, the clinic
receives a notification about that patient. The main advantage
of the hybrid system from the clinical point of view could be
summarized as follows:
(i) Classification and detecting of the epileptic seizures
and seizure-free signals from the EEG signal automat-
ically
10 International Journal of Biomedical Imaging

ACCURACY IN PERCENTAGE (%)

100
98 99
97.75 97.75 98 98.13 98.3
96 97.5
96.5
94 95.7
95
92 93.11
90
88 90
86
84
Bajaj et al. 2013

Martis et al. 2013

Pachori et al. 2014

Bajaj et al. 2012

The proposed method

Faust et al. 2010

Acharya et al. 2009

Yuan et al.2011

Naghsh-Nilchi et al. 2010

Patidar et al. 2017

Acharya et al. 2012

Kumar et al. 2015

PROPOSED SYSTESMS USED TO FOR THE COMPARSION

Figure 8: The total accuracy (%) of various methods employed to detect the disorder of the epilepsy.

(ii) The detection of the preictal phase from studying the each segment. After the dataset was constructed, a feature
healthy and ictal phase of each patient reduction algorithm based on firefly optimization was used to
(iii) The detection of the preictal phase that provided the reduce the irrelevant features and remove redundancy. Then,
ability to send warning alert to the physicians to an RF was trained to classify and predict the epileptic seizures
prepare the medical assessment for the patient and seizure-free EEG signals from the dataset. The experi-
mental results showed that the proposed method achieved
(iv) The proposed method being robust and reliable as its a satisfactory degree of 99% accuracy, 97% precision, 97%
performance was benchmarked using 10-fold cross- specificity, 98% recall, 98% F-measure, and 95% MCC at the
validation third level of decomposition.
(v) The dynamic behavior obtained from the firefly
algorithm which made the system adaptive to many Data Availability
features according to each case study.
(vi) A few sets of parameters required to analyze the EEG The dataset used to support the findings of this research was
signal typical three variables (𝑄, 𝑟, 𝐽). included in the article and can be found as a citation to “R.G.
Andrzejak, K. Lehnertz, F. Mormann, C. Rieke, P. David,
The limitations of this research were summarized as follows: C.E. Elger, Indications of Nonlinear Deterministic and Finite-
Dimensional Structures in Time Series of Brain Electrical
(i) The limited number of the studied subjects (typically
Activity: Dependence on Recording Region and Brain State,
100 per class)
Physical Review E, 64 (2001) 061907”.
(ii) The diagnosis process that may be reduced because of
depending on some additional software prerequisites.
Conflicts of Interest
5. Conclusion The authors declare that they have no conflicts of interest.

In this paper, an automated intelligent CAD tool has been

proposed to classify and detect epileptic seizures and seizure- References
free EEG signals. This method provided an EEG signal [1] Epilepsy Fact Sheet, 2018, http://www.who.int/mediacentre/
analysis using a hybrid data fusion method. The data fusion factsheets/fs999/en/.
method combined the collected features from two different [2] U. R. Acharya, S. V. Sree, G. Swapna, R. J. Martis, and J. S. Suri,
perspectives. In the first perspective, the EEG signal was “Automated EEG analysis of epilepsy: a review,” Knowledge-
considered as an image. Then, the image was converted to Based Systems, vol. 45, pp. 147–165, 2013.
a gray image and the GLCM was obtained to extract the [3] A. Puce and M. S. Hämäläinen, “A review of issues related
textures of the image such as contrast, correlation, power, and to data acquisition and analysis in EEG/MEG studies,” Brain
homogeneity. In the second perspective, the EEG signal was Sciences, vol. 7, no. 6, 2017.
divided into smaller segments using the TQWT to extract [4] V. Joshi, R. B. Pachori, and A. Vijesh, “Classification of ictal
the time and frequency features. A set of statistical, nonlinear and seizure-free EEG signals using fractional linear prediction,”
(chaotic), and power spectrum features were obtained from Biomedical Signal Processing and Control, vol. 9, pp. 1–5, 2014.
International Journal of Biomedical Imaging
[5] P. Ghaderyan, A. Abbasi, and M. H. Sedaaghi, “An efficient
seizure prediction method using KNN-based undersampling
and linear frequency measures,” Journal of Neuroscience Meth-
ods, vol. 232, pp. 134–142, 2014.
[6] R. B. Pachori and S. Patidar, “Epileptic seizure classification
in EEG signals using second-order difference plot of intrin-
sic mode functions,” Computer Methods and Programs in
Biomedicine, vol. 113, no. 2, pp. 494–502, 2014.
[7] A. R. Hassan and A. Subasi, “Automatic identification of
epileptic seizures from EEG signals using linear programming
boosting,” Computer Methods and Programs in Biomedicine, vol.
136, pp. 65–77, 2016.
[8] M. Sharma, A. Dhere, R. B. Pachori, and U. R. Acharya,
“An automatic detection of focal EEG signals using new class
of time–frequency localized orthogonal wavelet filter banks,”
Knowledge-Based Systems, vol. 118, pp. 217–227, 2017.
[9] O. Faust, U. R. Acharya, H. Adeli, and A. Adeli, “Wavelet-
based EEG processing for computer-aided seizure detection and
epilepsy diagnosis,” Seizure, vol. 26, pp. 56–64, 2015.
[10] Y. Kumar, M. L. Dewal, and R. S. Anand, “Relative wavelet
energy and wavelet entropy based epileptic brain signals clas-
sification,” Biomedical Engineering Letters, vol. 2, no. 3, pp. 147–
157, 2012.
[11] R. Sharma and R. B. Pachori, “Classification of epileptic seizures
in EEG signals based on phase space representation of intrinsic
mode functions,” Expert Systems with Applications, vol. 42, no.
3, pp. 1106–1117, 2015.
[12] V. Bajaj and R. B. Pachori, “Epileptic seizure detection based on
the instantaneous area of analytic intrinsic mode functions of
EEG signals,” Biomedical Engineering Letters, vol. 3, no. 1, pp.
17–21, 2013.
[13] Y. Kaya, M. Uyar, R. Tekin, and S. Yıldırım, “1D-local binary
pattern based feature extraction for classification of epileptic
EEG signals,” Applied Mathematics and Computation, vol. 243,
pp. 209–219, 2014.
[14] T. S. Kumar, V. Kanhangad, and R. B. Pachori, “Classification
of seizure and seizure-free EEG signals using local binary
patterns,” Biomedical Signal Processing and Control, vol. 15, pp.
33–40, 2015.
[15] M. Mursalin, Y. Zhang, Y. Chen, and N. V. Chawla, “Automated
epileptic seizure detection using improved correlation-based
feature selection with random forest classifier,” Neurocomputing,
vol. 241, pp. 204–214, 2017.
[16] L. Wang, W. Xue, Y. Li et al., “Automatic epileptic seizure
detection in EEG signals using multi-domain feature extraction
and nonlinear analysis,” Entropy, vol. 19, no. 6, 2017.
[17] Q. Yuan, W. Zhou, L. Zhang et al., “Epileptic seizure detection
based on imbalanced classification and wavelet packet trans-
form,” Seizure, vol. 50, pp. 99–108, 2017.
[18] S. Lahmiri, “Generalized Hurst exponent estimates differentiate
EEG signals of healthy and epileptic patients,” Physica A:
Statistical Mechanics and its Applications, vol. 490, pp. 378–385,
2018.
[19] U. R. Acharya, F. Molinari, S. V. Sree, S. Chattopadhyay, K. H.
Ng, and J. S. Suri, “Automated diagnosis of epileptic EEG using
entropies,” Biomedical Signal Processing and Control, vol. 7, no.
4, pp. 401–408, 2012.
[20] R. Dhiman, J. S. Saini, and Priyanka, “Genetic algorithms tuned
expert model for detection of epileptic seizures from EEG
signatures,” Applied Soft Computing, vol. 19, pp. 8–17, 2014.
11
[21] A. R. Hassan, S. Siuly, and Y. Zhang, “Epileptic seizure detection
in EEG signals using tunable-Q factor wavelet transform and
bootstrap aggregating,” Computer Methods and Programs in
Biomedicine, vol. 137, pp. 247–259, 2016.
[22] S. Patidar and T. Panigrahi, “Detection of epileptic seizure using
Kraskov entropy applied on tunable-Q wavelet transform of
EEG signals,” Biomedical Signal Processing and Control, vol. 34,
pp. 74–80, 2017.
[23] J. Jia, B. Goparaju, J. Song, R. Zhang, and M. B. Westover,
“Automated identification of epileptic seizures in EEG signals
based on phase space representation and statistical features in
the CEEMD domain,” Biomedical Signal Processing and Control,
vol. 38, pp. 148–157, 2017.
[24] T. Gandhi, B. K. Panigrahi, and S. Anand, “A comparative study
of wavelet families for EEG signal classification,” Neurocomput-
ing, vol. 74, no. 17, pp. 3051–3057, 2011.
[25] I. W. Selesnick, “Wavelet transform with tunable Q-factor,” IEEE
Transactions on Signal Processing, vol. 59, no. 8, pp. 3560–3575,
2011.
[26] S. Patidar and R. B. Pachori, “Classification of cardiac sound
signals using constrained tunable-Q wavelet transform,” Expert
Systems with Applications, vol. 41, no. 16, pp. 7161–7170, 2014.
[27] S. Patidar, R. B. Pachori, A. Upadhyay, and U. Rajendra Acharya,
“An integrated alcoholic index using tunable-Q wavelet trans-
form based features extracted from EEG signals for diagnosis
of alcoholism,” Applied Soft Computing, vol. 50, pp. 71–78, 2017.
[28] R. G. Andrzejak, K. Lehnertz, F. Mormann, C. Rieke, P. David,
and C. E. Elger, “Indications of nonlinear deterministic and
finite-dimensional structures in time series of brain electrical
activity: dependence on recording region and brain state,”
Physical Review E: Statistical, Nonlinear, and Soft Matter Physics,
vol. 64, no. 6, 2001.
[29] P. Swami, A. K. Godiyal, J. Santhosh, B. K. Panigrahi, M. Bhatia,
and S. Anand, “Robust expert system design for automated
detection of epileptic seizures using SVM classifier,” in Proceed-
ings of the 2014 3rd IEEE International Conference on Parallel,
Distributed and Grid Computing, PDGC 2014, pp. 219–222,
India, December 2014.
[30] P. Swami, T. K. Gandhi, B. K. Panigrahi, M. Tripathi, and S.
Anand, “A novel robust diagnostic model to detect seizures in
electroencephalography,” Expert Systems with Applications, vol.
56, pp. 116–130, 2016.
[31] H. Ocak, “Automatic detection of epileptic seizures in EEG
using discrete wavelet transform and approximate entropy,”
Expert Systems with Applications, vol. 36, no. 2, pp. 2027–2036,
2009.
[32] J.-H. Kang, Y. G. Chung, and S.-P. Kim, “An efficient detection
of epileptic seizure by differentiation and spectral analysis of
electroencephalograms,” Computers in Biology and Medicine,
vol. 66, pp. 352–356, 2015.
[33] S. Barua, M. U. Ahmed, C. Ahlstrom, S. Begum, and P. Funk,
“Automated EEG Artifact Handling with Application in Driver
Monitoring,” IEEE Journal of Biomedical and Health Informatics,
2017.
[34] G. E. Polychronaki, P. Y. Ktonas, S. Gatzonis et al., “Comparison
of fractal dimension estimation algorithms for epileptic seizure
onset detection,” Journal of Neural Engineering, vol. 7, no. 4,
2010.
[35] J. Gorecka, “Detection of ocular artifacts in EEG data using
the Hurst exponent,” in Proceedings of the 20th International
Conference on Methods and Models in Automation and Robotics,
MMAR 2015, pp. 931–933, August 2015.
12 International Journal of Biomedical Imaging

[36] F. Parastesh Karegar, A. Fallah, and S. Rashidi, “ECG based

human authentication with using Generalized Hurst Exponent,”
in Proceedings of the 25th Iranian Conference on Electrical
Engineering, ICEE 2017, pp. 34–38, May 2017.
[37] I. Fister, I. Fister Jr., X.-S. Yang, and J. Brest, “A comprehensive
review of firefly algorithms,” Swarm and Evolutionary Compu-
tation, vol. 13, no. 1, pp. 34–46, 2013.
[38] L. Zhang, K. Mistry, C. P. Lim, and S. C. Neoh, “Feature selec-
tion using firefly optimization for classification and regression
models,” Decision Support Systems, vol. 106, pp. 64–85, 2018.
[39] L. Breiman, “Random forests,” Machine Learning, vol. 45, no. 1,
pp. 5–32, 2001.
[40] T. Fawcett, “An introduction to ROC analysis,” Pattern Recogni-
tion Letters, vol. 27, no. 8, pp. 861–874, 2006.
[41] J. P. Kandhasamy and S. Balamurali, “Performance analysis
of classifier models to predict diabetes mellitus,” Procedia
Computer Science, vol. 47, pp. 45–51, 2015.
[42] G. Varoquaux, “Cross-validation failure: Small sample sizes lead
to large error bars,” NeuroImage, 2017.
[43] O. Faust, U. R. Acharya, L. C. Min, and B. H. C. Sputh, “Auto-
matic identification of epileptic and background eeg signals
using frequency domain parameters,” International Journal of
Neural Systems, vol. 20, no. 2, pp. 159–176, 2010.
[44] U. R. Acharya, C. K. Chua, T.-C. Lim, Dorithy, and J. S.
Suri, “Automatic identification of epileptic EEG signals using
nonlinear parameters,” Journal of Mechanics in Medicine and
Biology, vol. 9, no. 4, pp. 539–553, 2009.
[45] R. J. Martis, U. R. Acharya, J. H. Tan et al., “Application of
intrinsic time-scale decomposition (ITD) to EEG signals for
automated seizure prediction,” International Journal of Neural
Systems, vol. 23, no. 5, pp. 1557–1565, 2013.
[46] Q. Yuan, W. Zhou, S. Li, and D. Cai, “Epileptic EEG classification
based on extreme learning machine and nonlinear features,”
Epilepsy Research, vol. 96, no. 1-2, pp. 29–38, 2011.
[47] A. R. Naghsh-Nilchi and M. Aghashahi, “Epilepsy seizure
detection using eigen-system spectral estimation and Multiple
Layer Perceptron neural network,” Biomedical Signal Processing
and Control, vol. 5, no. 2, pp. 147–157, 2010.
[48] V. Bajaj and R. B. Pachori, “Classification of seizure and
nonseizure EEG signals using empirical mode decomposition,”
IEEE Transactions on Information Technology in Biomedicine,
vol. 16, no. 6, pp. 1135–1142, 2012.
 International Journal of

Rotating Advances in
Machinery Multimedia

The Scientific
Engineering
Journal of
Journal of

Hindawi
World Journal
Hindawi Publishing Corporation Hindawi
Sensors
Hindawi Hindawi
www.hindawi.com Volume 2018 http://www.hindawi.com
www.hindawi.com Volume 2018
2013 www.hindawi.com Volume 2018 www.hindawi.com Volume 2018 www.hindawi.com Volume 2018

Journal of

Control Science
and Engineering

Advances in
Civil Engineering
Hindawi Hindawi
www.hindawi.com Volume 2018 www.hindawi.com Volume 2018

Submit your manuscripts at

www.hindawi.com

Journal of
Journal of Electrical and Computer
Robotics
Hindawi
Engineering
Hindawi
www.hindawi.com Volume 2018 www.hindawi.com Volume 2018

VLSI Design
Advances in
OptoElectronics
International Journal of

International Journal of
Modelling &
Simulation
Aerospace
Hindawi Volume 2018
Navigation and
Observation
Hindawi
www.hindawi.com Volume 2018
in Engineering
Hindawi
www.hindawi.com Volume 2018
Engineering
Hindawi
www.hindawi.com Volume 2018
Hindawi
www.hindawi.com www.hindawi.com Volume 2018

International Journal of
International Journal of Antennas and Active and Passive Advances in
Chemical Engineering Propagation Electronic Components Shock and Vibration Acoustics and Vibration
Hindawi Hindawi Hindawi Hindawi Hindawi
www.hindawi.com Volume 2018 www.hindawi.com Volume 2018 www.hindawi.com Volume 2018 www.hindawi.com Volume 2018 www.hindawi.com Volume 2018